Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1319 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.9608. Min Range: -4.9608
Max Act: 4.8671. Min Act: -0.1700
Data Index: 1586250 (Python Code)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9608. Min Range: -4.9608
Max Act: 4.9608. Min Act: -0.1700
Data Index: 1648282 (Python Code)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9608. Min Range: -4.9608
Max Act: 4.7733. Min Act: -0.1700
Data Index: 1514322 (Python Code)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9608. Min Range: -4.9608
Max Act: 4.8046. Min Act: -0.1700
Data Index: 1466928 (Python Code)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9608. Min Range: -4.9608
Max Act: 4.7108. Min Act: -0.1700
Data Index: 1540832 (Python Code)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9608. Min Range: -4.9608
Max Act: 4.7421. Min Act: -0.1700
Data Index: 1376505 (Python Code)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9608. Min Range: -4.9608
Max Act: 4.7733. Min Act: -0.1700
Data Index: 1489882 (Python Code)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9608. Min Range: -4.9608
Max Act: 4.7421. Min Act: -0.1700
Data Index: 1514655 (Python Code)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9608. Min Range: -4.9608
Max Act: 4.8046. Min Act: -0.1700
Data Index: 1456173 (Python Code)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9608. Min Range: -4.9608
Max Act: 4.7421. Min Act: -0.1700
Data Index: 1366654 (Python Code)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9608. Min Range: -4.9608
Max Act: 4.7733. Min Act: -0.1700
Data Index: 1642065 (Python Code)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9608. Min Range: -4.9608
Max Act: 4.7108. Min Act: -0.1700
Data Index: 1577794 (Python Code)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9608. Min Range: -4.9608
Max Act: 4.7108. Min Act: -0.1700
Data Index: 1425267 (Python Code)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9608. Min Range: -4.9608
Max Act: 4.7108. Min Act: -0.1700
Data Index: 1624916 (Python Code)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9608. Min Range: -4.9608
Max Act: 4.6796. Min Act: -0.1700
Data Index: 1401385 (Python Code)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9608. Min Range: -4.9608
Max Act: 4.6796. Min Act: -0.1700
Data Index: 1566020 (Python Code)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9608. Min Range: -4.9608
Max Act: 4.6171. Min Act: -0.1700
Data Index: 1468622 (Python Code)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9608. Min Range: -4.9608
Max Act: 4.7108. Min Act: -0.1700
Data Index: 1395831 (Python Code)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9608. Min Range: -4.9608
Max Act: 4.6796. Min Act: -0.1700
Data Index: 1417024 (Python Code)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9608. Min Range: -4.9608
Max Act: 4.5858. Min Act: -0.1700
Data Index: 1433333 (Python Code)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #19